System and method for collecting, organizing, and curating customer engagements across multiple domains to provide contextual nurturing and alignment of customer journeys to business objectives

Abstract

A system and method for collecting, organizing, and curating customer engagements across multiple interactions and touch points. The disclosed method allows for a discovery of purposes, an accretion of micro-journeys for a plurality of customers and a contextual nurturing of those customers on respective journeys towards their next milestones using numerical, graphical, statistical, and heuristics-based methods and proposed memory layouts of the same. Real-time staging and processing of inbound factual data and inferential dimensions into a multipartite multidimensional space of the factual and inferential dimensions to enable the mapping of customer interactions with a brand and the digital encoding thereof.

The invention claimed is: 
     
         1 . An at least one non-transitory computer readable storage media having a plurality of program instructions and a machine learning module stored thereon that, when executed by an at least one processor having a connection to a network and a memory, directs an at least one computing apparatus to:
 continuously receive, via the connection to the network, a real-time digital interaction stream from a plurality of customers and directly organize said stream into said memory at a bitwise level;   analyze, utilizing the machine learning module, a plurality of customer viewpoints depicting a multi-dimensional digital representation of a plurality of customer-business interactions for a plurality of customers, the plurality of customer-business interactions comprising a plurality of factual dimensions and a plurality of inferred dimensions;   classify, utilizing the machine learning module, said plurality of customer-business interactions according to a hierarchy between a communication from a business and a customer action, among the plurality of customers;   determine, based on said hierarchy an at least one customer purpose for each of said plurality of customers, said at least one customer purpose in accordance with an at least one business goal;   utilize a plurality of trigonometric laws to compare within said multi-dimensional digital representation a plurality of customer actions in response to a plurality of customer communications to refine said at least one customer purpose;   encode, via the processor, said hierarchy and said plurality of customer-business interactions into a plurality of bead based memory structures on said memory, each bead comprising a fixed 512-bit allocation with a leading first two bits assigned to identify each element of said hierarchy, said bead-based memory structures instantiated at the bitwise level in system memory connected to said processor and configured to maintain a contiguous allocation of said plurality of bead-based memory structures; and   output said at least one proposed customer-business interaction for execution of a customer-facing process.   
     
     
         2 . The at least one non-transitory computer readable storage media of  claim 1 , wherein the machine learning module continuously updates the multi-dimensional digital representation in real-time by deducing a plurality of live co-ordinates for the plurality of factual dimensions based on contributions from a plurality of newer events from the real-time digital interaction stream and factors said plurality of newer events into a plurality of deducing values for said plurality of inferred dimensions. 
     
     
         3 . The at least one non-transitory computer readable the program instructions of  claim 1 , wherein said plurality of trigonometric laws is one or more from a group consisting of a law of cosines, a parallelogram law, and a polygon law. 
     
     
         4 . The at least one non-transitory computer readable storage media of  claim 3 , wherein said customer-facing process is selected from a group of processes, the group consisting of a transmission via the network of a message via email, a transmission of a short message service (SMS) notification via the network, a delivery of a push notification to a mobile application via the network, a causation of a pop-up message within a web interface via a user connection to the network, an initiation of a chatbot interaction via the network, and a generation of an in-application alert on a user device connected to the network. 
     
     
         5 . The at least one non-transitory computer readable storage media of  claim 1 , wherein said plurality of elements are domains comprising a hear element, a see element, a think element, and a do element, wherein said hear element comprises a selection of said customer-business interactions where said customer receives said customer communication, said see element comprises a selection of said customer-business interactions where said real-time digital interaction stream indicates said customer has registered said customer communication, said think element comprises a selection of said customer-business interactions where said real-time digital interaction stream indicates said customer has recognized a value of said customer communication, and said do element comprises a selection of said customer-business interactions where said real-time digital interaction stream indicates said customer has performed said customer action. 
     
     
         6 . The at least one non-transitory computer readable storage media of  claim 5 , wherein said at least one customer purpose is determined via the machine learning module. 
     
     
         7 . The at least one non-transitory computer readable storage media of  claim 6 , wherein said plurality of program instructions and said machine learning module stored thereon said non-transitory computer readable media are further programed to cause the processor to generate said at least one proposed customer-business interaction as a digital notification, customize content of the digital notification according to said hierarchy and said customer purpose, and transmit the digital notification over the network to a plurality of customer devices in real-time. 
     
     
         8 . The at least one non-transitory computer readable storage media of  claim 7 , wherein said plurality of customer communications are an at least one customer communication from a group of customer communications, the group consisting of a touchpoint, a value proposition, a dialogue, an offer, a voucher, a coupon, and a recommendation to switching from a first service to a second service. 
     
     
         9 . A method of collecting, organizing, and curating a plurality of customer engagements across multiple customer-business domains in a multi-dimensional digital representation of a plurality of customer-business interactions, the method comprising:
 on at least one computing device having a non-transitory computer readable storage media, a processor having a connection to a memory and a network, said non-transitory computer readable storage media with a plurality of program instructions and a machine learning module stored thereon:   continuously receiving, via the connection to the network, a real-time digital interaction stream from a plurality of customers and directly organize said stream into said memory at a bitwise level;   analyzing a plurality of customer viewpoints depicting a plurality of customer-business interactions for a plurality of customers, the customer-business interactions comprising a plurality of factual and a plurality of inferred dimensions, utilizing the machine learning module;   classifying said plurality of customer-business interactions according to a hierarchy between a customer communication from a business and a customer action, among the plurality of customers;   determining, based on said hierarchy an at least one customer purpose for each of said plurality of customers, said at least one customer purpose in accordance with an at least one business goal;   utilizing a plurality of trigonometric laws to compare within said multi-dimensional digital representation a plurality of customer actions in response to a plurality of customer communications to refine said at least one customer purpose; and   encoding, via the processor, said hierarchy and said plurality of customer-business interactions into a plurality of bead-based memory structures on said memory, each bead comprising a fixed 512-bit allocation with a leading first two bits assigned to identify each element of said hierarchy, said bead-based memory structures instantiated at the bitwise level in system memory connected to said processor and configured to maintain a contiguous allocation of said plurality of bead-based memory structures;   and outputting said at least one proposed customer-business interaction to a remote system via the connection to the network for execution of a customer-facing process.   
     
     
         10 . The method of  claim 9 , further comprising continuously updating via the machine learning module the multi-dimensional digital representation in real-time. 
     
     
         11 . The method of  claim 10 , further comprising deducing a plurality of live co-ordinates for the plurality of factual dimensions based on contributions from a plurality of newer events from the real-time digital interaction stream. 
     
     
         12 . The method of  claim 11 , further comprising factoring said plurality of newer events into a plurality of deducing values for said plurality of inferred dimensions. 
     
     
         13 . The method of  claim 9 , wherein said plurality of elements are domains comprising a hear element, a see element, a think element, and a do element, wherein said hear element comprises a selection of said customer-business interactions where said customer receives said customer communication, said see element comprises a selection of said customer-business interactions where said real-time digital interaction stream indicates said customer has registered said customer communication, said think element comprises a selection of said customer-business interactions where said real-time digital interaction stream indicates said customer has recognized a value of said customer communication, and said do element comprises a selection of said customer-business interactions where said real-time digital interaction stream indicates said customer has performed said customer action. 
     
     
         14 . The method of  claim 13 , further comprising determining said at least one customer purpose via the machine learning module. 
     
     
         15 . The method of  claim 14 , further comprising determining a level of completeness for said plurality of elements via said machine learning module. 
     
     
         16 . A system for collecting, organizing, and curating a plurality of customer engagements across multiple customer-business domains in a multi-dimensional digital representation of a plurality of customer-business interactions, the system comprising:
 an at least one computing device having an at least one non-transitory computer readable storage media having a plurality of program instructions and a machine learning module stored thereon, an at least one processor, a network connection, and an at least one memory, the computing device in continuous receipt of a real-time digital interaction stream from a plurality of customers and directly organize said stream into said memory at a bitwise level, the processor in communication with the non-transitory computer readable storage media directs the at least one computing device to:   analyze, utilizing the machine learning module, a plurality of customer viewpoints depicting a multi-dimensional digital representation of a plurality of customer-business interactions for a plurality of customers, the customer-business interactions comprising a plurality of factual dimensions and a plurality of inferred dimensions;   classify, utilizing the machine learning module, said plurality of customer-business interactions according to a hierarchy between a communication from a business and a customer action, among the plurality of customers;   determine, based on said hierarchy an at least one customer purpose for each of said plurality of customers, said at least one customer purpose in accordance with an at least one business goal;   utilize a plurality of trigonometric laws to compare within said multi-dimensional digital representation a plurality of customer actions in response to a plurality of customer communications to refine said at least one customer purpose;   encode, via the processor, said hierarchy and said plurality of customer-business interactions into a plurality of bead-based memory structures on said memory, each bead comprising a fixed 512-bit allocation with a leading first two bits assigned to identify each element of said hierarchy, said bead-based memory structures instantiated at the bitwise level in system memory connected to said processor and configured to maintain a contiguous allocation of said plurality of bead-based memory structures;   and output said at least one proposed customer-business interaction to a remote system via the network connection for execution of a customer-facing process.   
     
     
         17 . The system of  claim 16 , wherein said at least one customer purpose is determined via the machine learning module. 
     
     
         18 . The system of  claim 16 , wherein said multi-dimensional digital representation is modelled as an affine space. 
     
     
         19 . The system of  claim 16 , wherein said plurality of elements are domains comprising a hear element, a see element, a think element, and a do element, wherein said hear element comprises a selection of said customer-business interactions where said customer receives said customer communication, said see element comprises a selection of said customer-business interactions where said real-time digital interaction stream indicates said customer has registered said customer communication, said think element comprises a selection of said customer-business interactions where said real-time digital interaction stream indicates said customer has recognized a value of said customer communication, and said do element comprises a selection of said customer-business interactions where said real-time digital interaction stream indicates said customer has performed said customer action. 
     
     
         20 . The system of  claim 16 , wherein said at least one customer purpose is determined via the machine learning module and wherein a level of completeness for said plurality of elements is determined via said machine learning module.